Real-time surface of revolution reconstruction on dense SLAM
Résumé
We present a fast and accurate method for reconstructing surfaces of revolution (SoR) on 3D data and its application to structural modeling of a cluttered scene in real-time. To estimate a SoR axis, we derive an approximately linear cost function for fast convergence. Also, we design a framework for reconstructing SoR on dense SLAM. In the experiment results, we show our method is accurate, robust to noise and runs in real-time.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...